Best LLMs for 10 GB VRAM
作者： Jakub Rusinowski · 最后更新： 2026年7月15日
These are the strongest local models that fit entirely in 10 GB of VRAM, ranked by capability, with the quantization level and estimated tokens/sec needed to fit.
GPUs at This Tier
Ranked Models
| Qwen 2.5 Family — Qwen 2.5 14B Instruct | Q4_K_M · 8.4525 GB |
| Qwen 3 — Qwen 3 14B | Q4_K_M · 8.935500000000001 GB |
| DeepSeek R1 — DeepSeek R1 Distill Qwen 14B | Q4_K_M · 8.4525 GB · ~23 tok/s on Intel Arc B570 |
| Phi-4 Family — Phi-4 (14B) | Q4_K_M · 8.4525 GB |
| Granite 3.0 — Granite 3.0 8B Instruct | Q4_K_M · 4.83 GB · ~36 tok/s on Intel Arc B570 |
| Bonsai 27B — Ternary Bonsai 27B | Ternary (1.58-bit, ~1.71 bpw) · 5.77125 GB · ~30 tok/s on Intel Arc B570 |
| Qwen 2.5 Family — Qwen 2.5 7B Instruct | Q4_K_M · 4.5885 GB · ~40 tok/s on Intel Arc B570 |
| Qwen 3 — Qwen 3 8B | Q4_K_M · 4.950749999999999 GB · ~35 tok/s on Intel Arc B570 |
| DeepSeek R1 — DeepSeek R1 Distill Llama 8B | Q4_K_M · 4.83 GB · ~36 tok/s on Intel Arc B570 |
| Mistral Family — Mistral NeMo 12B | Q4_K_M · 7.245 GB · ~26 tok/s on Intel Arc B570 |
| Gemma 3 — Gemma 3 12B Instruct | Q4_K_M · 7.245 GB · ~24 tok/s on Intel Arc B570 |
| InternLM 3 — InternLM 3 8B Instruct | Q4_K_M · 5.313000000000001 GB · ~35 tok/s on Intel Arc B570 |
| Qwen 3.5 — Qwen 3.5 9B | Q4_K_M · 5.43375 GB · ~33 tok/s on Intel Arc B570 |
| Bonsai 27B — 1-bit Bonsai 27B | 1-bit (binary, ~1.125 bpw) · 3.796875 GB · ~41 tok/s on Intel Arc B570 |
| Yi 1.5 Family — Yi 1.5 9B Chat | Q4_K_M · 5.3311125 GB · ~34 tok/s on Intel Arc B570 |
购买此硬件 Intel Arc B570 10GB — 10 GB VRAM · 150 W board power立即云端部署 RunPod 上的 RTX 4090 — 低至 $0.34/小时 · 价格核实于 2026-07
或在 Vast.ai 比较，低至 $0.35/小时 (typical low · varies)
作为亚马逊联盟成员，我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金，您无需额外付费。
FAQ
What LLMs run well with 10 GB VRAM?
Qwen 2.5 Family, Qwen 3, DeepSeek R1, Phi-4 Family, Granite 3.0 all fit in 10 GB VRAM.
Which GPUs have 10 GB VRAM?
Intel Arc B570, NVIDIA GeForce RTX 3080 (10GB), NVIDIA GeForce RTX 3080 12GB, Intel Arc B580.
Can-I-Run Pages Near 10 GB
- DeepSeek R1 on NVIDIA GeForce RTX 3080 (10GB)
- DeepSeek R1 on Intel Arc B570
- Llama 3.3 on NVIDIA GeForce RTX 3080 (10GB)
- Llama 3.3 on Intel Arc B570
- Llama 3.1 Family on NVIDIA GeForce RTX 3080 (10GB)
- Llama 3.1 Family on Intel Arc B570
- Command R Family on NVIDIA GeForce RTX 3080 (10GB)
- Command R Family on Intel Arc B570